deepnetts.net.layers

Interface Layer

All Known Implementing Classes:

AbstractLayer, ConvolutionalLayer, FlattenLayer, FullyConnectedLayer, InputLayer, MaxPoolingLayer, OutputLayer, SoftmaxOutputLayer

public interface Layer

Common base interface for all types of neural network layers. Layer is a basic building block of a neural network NeuralNetwork. Neural network typically consists of a sequence of layers. Layer performs mathematical operations on it's inputs, and provides output to yhe next layer as an input.

See Also:

AbstractLayer, LayerType, deepnetts.net.layers

Method Summary

Modifier and Type	Method and Description
void	backward() Performs weight parameters adjustment in backward pass during training of a neural network.
void	forward() Performs layer calculation in forward pass of a neural network.
Tensor	getDeltas() Returns layer deltas/errors (as a tensor).
Tensor	getOutputs() Returns layer outputs (as a tensor).

Method Detail

forward

void forward()

Performs layer calculation in forward pass of a neural network.

backward

void backward()

Performs weight parameters adjustment in backward pass during training of a neural network.

getOutputs

Tensor getOutputs()

Returns layer outputs (as a tensor).

Returns:

layer output as a tensor

getDeltas

Tensor getDeltas()

Returns layer deltas/errors (as a tensor). Deltas are accumulated errors propagated from the next layer.

Returns:

layer deltas tensor